Towards integrating spatial localization in convolutional neural networks for brain image segmentation

TL;DR

This paper enhances brain MRI segmentation by integrating spatial constraints into CNNs, reducing prediction inconsistencies and improving accuracy in identifying cerebral structures.

Contribution

It introduces novel methods to incorporate spatial information into CNNs for brain image segmentation, improving consistency and accuracy.

Findings

Spatial constraints reduce segmentation inconsistencies

Using landmarks and probability atlas improves accuracy

Multi-scale patch CNN benefits from spatial information

Abstract

Semantic segmentation is an established while rapidly evolving field in medical imaging. In this paper we focus on the segmentation of brain Magnetic Resonance Images (MRI) into cerebral structures using convolutional neural networks (CNN). CNNs achieve good performance by finding effective high dimensional image features describing the patch content only. In this work, we propose different ways to introduce spatial constraints into the network to further reduce prediction inconsistencies. A patch based CNN architecture was trained, making use of multiple scales to gather contextual information. Spatial constraints were introduced within the CNN through a distance to landmarks feature or through the integration of a probability atlas. We demonstrate experimentally that using spatial information helps to reduce segmentation inconsistencies.